Topological preservation techniques for nonlinear process monitoring. (8th May 2015)

• Record Type: Journal Article
• Authors: Robertson, G.; Thomas, M.C.; Romagnoli, J.A.
• Is Part Of: Computers & chemical engineering. Volume 76(2015)
• Page Start: 1
• Page End: 16
• Publication Date: 2015-05-08
• Subjects: Process monitoring -- Fault detection -- Fault diagnosis -- Self-organizing maps -- Gaussian mixture model; Chemical engineering -- Data processing -- Periodicals; 660.0285
• DOI: 10.1016/j.compchemeng.2015.02.002
• Languages: English
• ISSNs: 0098-1354

Abstract

Highlights: A methodology for designing data-driven monitoring schemes was given. A novel topological preservation technique was proposed using self-organizing maps. Fault detection, fault identification, and fault diagnosis tasks were performed. The approach was applied to the Tennessee Eastman Process. Improvements of distance preservation techniques and other SOM approaches were shown. Abstract: This work proposes a novel approach for the offline development and online implementation of data-driven process monitoring (PM) using topological preservation techniques, specifically self-organizing maps (SOM). Previous topological preservation PM applications have been restricted due to the lack of monitoring and diagnosis tools. In the proposed approach, the capabilities of SOM are further extended so that all aspects of PM can be performed in a single environment. First for fault detection, using SOM's vector quantization abilities, an SOM-based Gaussian mixture model (GMM) is proposed to define the normal region. For identification, an SOM-based contribution plot is proposed to identify the variables most responsible for the fault. This is done by analyzing the residual of the faulty point and an SOM model of the normal region used in fault detection. The data points are projected on the model by locating the best matching unit (BMU) of the point. Finally, for fault diagnosis a procedure is formulated involving the concept of multiple self-organizing maps (MSOM), creating a map for each fault. This allows the ability to include new faults without directly affecting previously characterized faults. A Tennessee Eastman Process (TEP) application is performed on dynamic faults such as random variations, sticky valves and a slow drift in kinetics. Previous studies of the TEP have considered particular feed-step-change faults. Results indicate an excellent performance when compared to linear and nonlinear distance preservation techniques and standard nonlinear SOM approaches in fault diagnosis and identification.